I'm a PhD candidate in Computer Science working with David Jensen in the Knowledge Discovery Laboratory at UMass Amherst and Vikash Mansinghka in the Probabilistic Computing Project at MIT. I study methods that combine expert knowledge of mechanisms with causal machine learning, enabling AI-assisted scientific discovery and explainable AI. In practice, my work focusses on probabilistic programming and Bayesian nonparametric approaches to causal inference with observational, experimental and quasi-experimental data. When I'm not reading, writing, or talking about models, you're likely to find me lost in the woods with my
puppy dog Mira.
A Simulation-Based Test of Identifiability for Bayesian Causal Inference
Sam Witty, David Jensen, Vikash Mansinghka (2021).
arXiv preprint arXiv:2102.11761 [bibtex]
Causal Inference using Gaussian Processes with Structured Latent Confounders
Sam Witty, Kenta Takatsu, David Jensen, Vikash Mansinghka (2020).
International Conference on Machine Learning. [bibtex]
Bayesian Causal Inference via Probabilistic Program Synthesis
Sam Witty*, Alexander Lew*, David Jensen, Vikash Mansinghka (2020).
Second Conference on Probabilistic Programming [bibtex]
Measuring and Characterizing Generalization in Deep Reinforcement Learning
Sam Witty, Jun Ki Lee, Emma Tosch, Akanksha Atrey, Michael Littman, David Jensen (2018).
arXiv preprint arXiv:1812.02868 [bibtex]
(Short Version Published at the NeurIPS CRACT Workshop.)
Causal Graphs vs. Causal Programs: The Case of Conditional Branching.
Sam Witty, David Jensen (2018).
First Conference on Probabilistic Programming. [bibtex]
Belief-Space Planning for Automated Malware Defense.
Justin Svegliato, Sam Witty, Amir Houmansadr, Shlomo Zilberstein (2018).
IJCAI Workshop on AI for Internet of Things. [bibtex]